© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    import module or add property

    np_acts-logits-general · gemini-2.5-flash-lite

    LaTeX package inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cracks
    0.39
    ت
    0.39
    Quote
    0.38
     навіть
    0.38
     nawet
    0.37
     அடித்த
    0.37
    䧼
    0.36
     даже
    0.36
     सियासी
    0.35
     Inequality
    0.35
    POSITIVE LOGITS
    ediaan
    0.43
    特典
    0.40
     hydroxyl
    0.40
    ábado
    0.40
     ادي
    0.39
     namani
    0.38
     comuns
    0.38
    gaxModule
    0.37
    ᅪ
    0.37
    पीरियंस
    0.37
    Activations Density 0.000%

    No Known Activations